| Abstract Title: | How to deliver small sensor devices that are consistently accurate |
| Presenter Name: | Mr Bruno Beloff |
| Company/Organisation: | South Coast Science Limited |
| Country: | United Kingdom |
Abstract Information :
Small, low-cost and consistent in their behaviour, gas electrochemical sensors promise much. However, the behaviour of these sensors in real-world environments is complex. Because of this, extracting precise gas concentration signals is both rewarding and challenging.Following several years of collocation with reference equipment, South Coast Science has developed a set of machine learning (ML) models that separate pollutant concentration from environmental noise. The company initially focused on particulate modelling, receiving MCERTS data quality approval for PM2.5 and PM10, without the need to condition the air being measured. The company then turned its attention to reactive gases.Modelling with gas electrochemical sensors brings its own challenges, not least because each individual sensor has its own unique qualities. The model output is precise, but can a ML model that had been trained using one, collocated sensor be applied to others without loss of accuracy? In other words, can a model be calibrated to each specific sensor in each instrument? The manufacture of small sensor devices at South Coast Science now incorporates the answers to this question. As a result, the company is changing customer expectations for small sensor equipment.rn
